Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1985 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.5897. Min Range: -6.5897
Max Act: 6.5897. Min Act: -0.1700
Data Index: 1126517 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5897. Min Range: -6.5897
Max Act: 6.4959. Min Act: -0.1700
Data Index: 820137 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5897. Min Range: -6.5897
Max Act: 6.4334. Min Act: -0.1700
Data Index: 1044001 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5897. Min Range: -6.5897
Max Act: 6.3397. Min Act: -0.1700
Data Index: 664940 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5897. Min Range: -6.5897
Max Act: 6.4022. Min Act: -0.1700
Data Index: 529042 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5897. Min Range: -6.5897
Max Act: 6.3397. Min Act: -0.1700
Data Index: 336151 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5897. Min Range: -6.5897
Max Act: 6.3084. Min Act: -0.1700
Data Index: 118935 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5897. Min Range: -6.5897
Max Act: 6.3709. Min Act: -0.1700
Data Index: 459990 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5897. Min Range: -6.5897
Max Act: 6.2772. Min Act: -0.1700
Data Index: 475272 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5897. Min Range: -6.5897
Max Act: 6.1834. Min Act: -0.1700
Data Index: 1219586 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5897. Min Range: -6.5897
Max Act: 6.2147. Min Act: -0.1700
Data Index: 580554 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5897. Min Range: -6.5897
Max Act: 6.2459. Min Act: -0.1700
Data Index: 561467 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5897. Min Range: -6.5897
Max Act: 6.1209. Min Act: -0.1700
Data Index: 1259491 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5897. Min Range: -6.5897
Max Act: 6.0897. Min Act: -0.1700
Data Index: 1061134 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5897. Min Range: -6.5897
Max Act: 6.1209. Min Act: -0.1700
Data Index: 404024 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5897. Min Range: -6.5897
Max Act: 6.0584. Min Act: -0.1700
Data Index: 104142 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5897. Min Range: -6.5897
Max Act: 6.0584. Min Act: -0.1700
Data Index: 830162 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5897. Min Range: -6.5897
Max Act: 6.0272. Min Act: -0.1700
Data Index: 1115063 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5897. Min Range: -6.5897
Max Act: 6.0897. Min Act: -0.1700
Data Index: 670164 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5897. Min Range: -6.5897
Max Act: 6.0897. Min Act: -0.1700
Data Index: 719244 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19